ClawHub
Back to skill

Security audit

Contentstack Content Management

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Contentstack management connector with write capability, so users should review changes before approving them.

Install only if you intend to let your agent use an OOMOL-connected Contentstack account. Treat create and update actions as real CMS changes: verify the stack, content type, entry, payload, and resulting publishing workflow before approving any write.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The skill description and instructions say to use this skill for ANY Contentstack Content Management request and instead of calling the API directly, which creates an overly broad routing trigger. This can cause the agent to invoke a write-capable skill for loosely related requests or ambiguous user intent, increasing the chance of unintended data access or state-changing operations in Contentstack.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal